e-localisaion, Finalists 2012
Text to Speech synthesis is the process of converting inputtexttospeech.Theaimis to develop text-to-speech synthesis systems forIndian languages for exampleHindi,Bengali,Marathi,Telugu,TamilandMalayalam.The focus is to bring togetherthe expertise across these organizationsand provide a common platform and interface that can enable others to seamlessly integratethe synthesis systems into their products, and enhance the quality ofTTSforIndian languages.The goals of the project are vocabulary independent text to speech synthesis in Indian languages, namely Bengali, Hindi, Malayalam, Marathi,Tamil and Telugu and the integration withscreen readers Development work carried outfrom February 2009 to March 2012 componentsof a text-to-speech system.The components of a text-to-speech system could be broadly categorized as text processing and methods of speech generation. In the real world, the typicalinput to a text-to-speech system is text as available in electronic documents, news papers,blogs or emails.The text available notjust a sequence of words available in a standard dictionarysince it also contains numbers and graphics which makes the project a complex task.
The Local Language Dictionary was inaugurated in 2000 with the goal to use ICT technology to convert the language barrier into a language bridge. The offline Local Language Dictionary Software can be installed on computers and Laptops as well asapplications on Mobile Phone and tablets. The Online Local Language Dictionary Webservices are available on all web browsers along with plug-ins and widgets for all majorWeb browsers.The Offline Local Language Dictionary can also be availed as SMS serviceon all types of Mobile.Additionally websites in 10 different Indian languages are available including Marathi,Hindi,Gujarati,Tamil,Telugu, Kannada, Malayalam, Bengali, Punjabi and Sanskrit.The websites rank among the most favored websites for local languagereferences.The main objective of the project is to break down language barriers to beingdifferent regions and cultures closer together for the purpose of a peaceful living butalso to enable communication for economic reasons to foster social economic advancement of the excluded sections within Indian society.
FUEL aims at solving the problem of inconsistency and lack of standardization in software translation across the platform. The effort of FUEL is unique. It is a set of stepscombined with any content generating organization or a team involved with the goalof creating localized content adopted in ensured consistent high quality. Including this,FUEL is having a version control system allowing evolution of development, a bug trackerand ticketing system and a mailing list. Collaborative innovation is the most importantaspect here FUEL.The project is an open source effort that aims to solve the problem ofinconsistency and lack of standardization in computer software localization. FUEL works to create linguistic and technical resources like standardized terminology resources,computer translation styles, convention guides, and assessment methodologies. RecentlyGovt of Maharashtra has chosen FUEL for its e-Governance standard for example. TheFUEL Desktop module exists in Hindi created for the Hindi language community members.The members of the Hindi language community can use the application for email,browsing, and editing.
As the title of the project states the initiative visualized the project as one to nurture and protect the major languages of the North-East via computerized technology to ensure that these languages and the populations of the geo-linguistic region in question gain their rightful place on the digital map. The project was conducted under the aegis of the Department of Information technology,Government of India in partnership with different Universities such as Guwahati University, North Bengal University and Manipur University. The project’s main objective was to work hand-in-hand with our partners and acquaint them with tools for development of grass-roots technologies to ensure sustained growth of these languages on the digital medium. To ensure localization, CLDR’s for these languages were devised so that operating systems could be localized in these languages.Web-pages made in these languages need to beW3C compliant. Once these grass-rootsare created, the main task was that of development of Linguistic Resources in the formof the development of MAT dictionaries for eventual machine translation along with theinstallment of a spell-checker.